基于对象大小的缓存策略
Caching Policies based on Object Sizes
AI总结:
该研究针对不同缓存大小与工作负载,评估考虑对象长度的缓存驱逐策略,针对分段缓存设计混合策略,并为SIEVE及其扩展版本开发工作集近似方法。
摘要:
我们针对不同缓存大小(成本)和不同工作负载,评估考虑被缓存对象长度的驱逐策略,工作负载包括独立引用模型和真实生产轨迹;特别针对分段缓存考虑混合策略,为SIEVE及其感知长度的扩展版本开发了工作集近似方法。
英文摘要:
We evaluate eviction policies that consider the lengths of the objects being cached for different cache sizes (cost) and different workloads. Workloads include the Independent Reference Model and real-world production traces. In particular, hybrid policies are considered for segmented caches. A working-set approximation is developed for SIEVE as well as its length-aware extension.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。